EDA on Black Friday Sale¶
In [1]:
#import libaries
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly
import plotly.graph_objects as go
import plotly.express as px
import rfit
Cleaning the data¶
In [2]:
df = pd.read_csv("https://ccadroit.s3.amazonaws.com/cloudComputing/train.csv")
print(df)
df = df.drop(["User_ID","Product_ID"],axis=1)
df.head()
df.tail()
Out[2]:
Encoding Catagorical¶
In [3]:
from sklearn.preprocessing import LabelEncoder
df['Gender'] = LabelEncoder().fit_transform(df['Gender'])
#df['Age'] = LabelEncoder().fit_transform(df['Age'])
df['City_Category'] = LabelEncoder().fit_transform(df['City_Category'])
df['Product_Category_2'] =df['Product_Category_2'].fillna(0).astype('int64')
df['Product_Category_3'] =df['Product_Category_3'].fillna(0).astype('int64')
df.head()
df.tail()
Out[3]:
Check null values¶
In [4]:
df.isnull().sum()/df.shape[0]*100
Out[4]:
EDA¶
Question 1¶
Who spend much on Black Friday Sale?¶
In [5]:
fig = px.box(df, x="Gender", y="Purchase")
fig.update_traces(quartilemethod="exclusive") # or "inclusive", or "linear" by default
fig.show()
Finding: Men spend much on Black Friday sale
Question 2¶
People between what age are more likely to purchsase?¶
In [6]:
sns.countplot(df['Age'])
plt.title('Distribution of Age')
plt.xlabel('Different Categories of Age')
plt.show()
Finding: People between age 26-35 are more interested on black Friday Shopping
Question 3¶
Between married and unmarried who are more active on blackfriday sale¶
In [7]:
df.groupby("Marital_Status").mean()["Purchase"]
df.groupby("Marital_Status").mean()["Purchase"].plot(kind='bar')
plt.title("Marital_Status and Purchase Analysis")
plt.show()
Finding: Unmarried are more active on blackfriday sale
Question 4¶
Look for change in the categories of city with highest purchases. And are buying more among new comer and longest people live in city.¶
In [8]:
sns.countplot(df['City_Category'])
plt.show()
Finding: It is observed that city category 2 has made the most number of puchases.
In [9]:
df.groupby("City_Category").mean()["Purchase"].plot(kind='bar')
plt.title("City Category and Purchase Analysis")
plt.show()
However, the city whose buyers spend the most is city type 2
In [10]:
sns.countplot(df['Stay_In_Current_City_Years'])
plt.show()
Finding:It looks like the longest someone is living in that city the less prone they are to buy new things.